Merge tag 'kvm-s390-next-4.7-2' of git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into HEAD
KVM: s390: features and fixes for 4.7 part2
- Use hardware provided information about facility bits that do not
need any hypervisor activitiy
- Add missing documentation for KVM_CAP_S390_RI
- Some updates/fixes for handling cpu models and facilities
diff --git a/Documentation/virtual/kvm/devices/s390_flic.txt b/Documentation/virtual/kvm/devices/s390_flic.txt
index 8478de1..6b0e115 100644
--- a/Documentation/virtual/kvm/devices/s390_flic.txt
+++ b/Documentation/virtual/kvm/devices/s390_flic.txt
@@ -74,7 +74,7 @@
KVM_DEV_FLIC_ADAPTER_MODIFY
Modifies attributes of an existing I/O adapter interrupt source. Takes
- a kvm_s390_io_adapter_req specifiying the adapter and the operation:
+ a kvm_s390_io_adapter_req specifying the adapter and the operation:
struct kvm_s390_io_adapter_req {
__u32 id;
diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index f6b1279..942b8f6 100644
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@@ -747,7 +747,7 @@
uint32_t kvm_mips_read_count(struct kvm_vcpu *vcpu);
void kvm_mips_write_count(struct kvm_vcpu *vcpu, uint32_t count);
-void kvm_mips_write_compare(struct kvm_vcpu *vcpu, uint32_t compare);
+void kvm_mips_write_compare(struct kvm_vcpu *vcpu, uint32_t compare, bool ack);
void kvm_mips_init_count(struct kvm_vcpu *vcpu);
int kvm_mips_set_count_ctl(struct kvm_vcpu *vcpu, s64 count_ctl);
int kvm_mips_set_count_resume(struct kvm_vcpu *vcpu, s64 count_resume);
diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c
index b37954c..b8b7860e 100644
--- a/arch/mips/kvm/emulate.c
+++ b/arch/mips/kvm/emulate.c
@@ -302,12 +302,31 @@
*/
static uint32_t kvm_mips_read_count_running(struct kvm_vcpu *vcpu, ktime_t now)
{
- ktime_t expires;
+ struct mips_coproc *cop0 = vcpu->arch.cop0;
+ ktime_t expires, threshold;
+ uint32_t count, compare;
int running;
- /* Is the hrtimer pending? */
+ /* Calculate the biased and scaled guest CP0_Count */
+ count = vcpu->arch.count_bias + kvm_mips_ktime_to_count(vcpu, now);
+ compare = kvm_read_c0_guest_compare(cop0);
+
+ /*
+ * Find whether CP0_Count has reached the closest timer interrupt. If
+ * not, we shouldn't inject it.
+ */
+ if ((int32_t)(count - compare) < 0)
+ return count;
+
+ /*
+ * The CP0_Count we're going to return has already reached the closest
+ * timer interrupt. Quickly check if it really is a new interrupt by
+ * looking at whether the interval until the hrtimer expiry time is
+ * less than 1/4 of the timer period.
+ */
expires = hrtimer_get_expires(&vcpu->arch.comparecount_timer);
- if (ktime_compare(now, expires) >= 0) {
+ threshold = ktime_add_ns(now, vcpu->arch.count_period / 4);
+ if (ktime_before(expires, threshold)) {
/*
* Cancel it while we handle it so there's no chance of
* interference with the timeout handler.
@@ -329,8 +348,7 @@
}
}
- /* Return the biased and scaled guest CP0_Count */
- return vcpu->arch.count_bias + kvm_mips_ktime_to_count(vcpu, now);
+ return count;
}
/**
@@ -420,32 +438,6 @@
}
/**
- * kvm_mips_update_hrtimer() - Update next expiry time of hrtimer.
- * @vcpu: Virtual CPU.
- *
- * Recalculates and updates the expiry time of the hrtimer. This can be used
- * after timer parameters have been altered which do not depend on the time that
- * the change occurs (in those cases kvm_mips_freeze_hrtimer() and
- * kvm_mips_resume_hrtimer() are used directly).
- *
- * It is guaranteed that no timer interrupts will be lost in the process.
- *
- * Assumes !kvm_mips_count_disabled(@vcpu) (guest CP0_Count timer is running).
- */
-static void kvm_mips_update_hrtimer(struct kvm_vcpu *vcpu)
-{
- ktime_t now;
- uint32_t count;
-
- /*
- * freeze_hrtimer takes care of a timer interrupts <= count, and
- * resume_hrtimer the hrtimer takes care of a timer interrupts > count.
- */
- now = kvm_mips_freeze_hrtimer(vcpu, &count);
- kvm_mips_resume_hrtimer(vcpu, now, count);
-}
-
-/**
* kvm_mips_write_count() - Modify the count and update timer.
* @vcpu: Virtual CPU.
* @count: Guest CP0_Count value to set.
@@ -540,23 +532,42 @@
* kvm_mips_write_compare() - Modify compare and update timer.
* @vcpu: Virtual CPU.
* @compare: New CP0_Compare value.
+ * @ack: Whether to acknowledge timer interrupt.
*
* Update CP0_Compare to a new value and update the timeout.
+ * If @ack, atomically acknowledge any pending timer interrupt, otherwise ensure
+ * any pending timer interrupt is preserved.
*/
-void kvm_mips_write_compare(struct kvm_vcpu *vcpu, uint32_t compare)
+void kvm_mips_write_compare(struct kvm_vcpu *vcpu, uint32_t compare, bool ack)
{
struct mips_coproc *cop0 = vcpu->arch.cop0;
+ int dc;
+ u32 old_compare = kvm_read_c0_guest_compare(cop0);
+ ktime_t now;
+ uint32_t count;
/* if unchanged, must just be an ack */
- if (kvm_read_c0_guest_compare(cop0) == compare)
+ if (old_compare == compare) {
+ if (!ack)
+ return;
+ kvm_mips_callbacks->dequeue_timer_int(vcpu);
+ kvm_write_c0_guest_compare(cop0, compare);
return;
+ }
- /* Update compare */
+ /* freeze_hrtimer() takes care of timer interrupts <= count */
+ dc = kvm_mips_count_disabled(vcpu);
+ if (!dc)
+ now = kvm_mips_freeze_hrtimer(vcpu, &count);
+
+ if (ack)
+ kvm_mips_callbacks->dequeue_timer_int(vcpu);
+
kvm_write_c0_guest_compare(cop0, compare);
- /* Update timeout if count enabled */
- if (!kvm_mips_count_disabled(vcpu))
- kvm_mips_update_hrtimer(vcpu);
+ /* resume_hrtimer() takes care of timer interrupts > count */
+ if (!dc)
+ kvm_mips_resume_hrtimer(vcpu, now, count);
}
/**
@@ -1095,9 +1106,9 @@
/* If we are writing to COMPARE */
/* Clear pending timer interrupt, if any */
- kvm_mips_callbacks->dequeue_timer_int(vcpu);
kvm_mips_write_compare(vcpu,
- vcpu->arch.gprs[rt]);
+ vcpu->arch.gprs[rt],
+ true);
} else if ((rd == MIPS_CP0_STATUS) && (sel == 0)) {
unsigned int old_val, val, change;
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index 70ef1a4..23b2094 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -1079,7 +1079,8 @@
r = KVM_COALESCED_MMIO_PAGE_OFFSET;
break;
case KVM_CAP_MIPS_FPU:
- r = !!cpu_has_fpu;
+ /* We don't handle systems with inconsistent cpu_has_fpu */
+ r = !!raw_cpu_has_fpu;
break;
case KVM_CAP_MIPS_MSA:
/*
@@ -1555,8 +1556,10 @@
/* Disable MSA & FPU */
disable_msa();
- if (vcpu->arch.fpu_inuse & KVM_MIPS_FPU_FPU)
+ if (vcpu->arch.fpu_inuse & KVM_MIPS_FPU_FPU) {
clear_c0_status(ST0_CU1 | ST0_FR);
+ disable_fpu_hazard();
+ }
vcpu->arch.fpu_inuse &= ~(KVM_MIPS_FPU_FPU | KVM_MIPS_FPU_MSA);
} else if (vcpu->arch.fpu_inuse & KVM_MIPS_FPU_FPU) {
set_c0_status(ST0_CU1);
@@ -1567,6 +1570,7 @@
/* Disable FPU */
clear_c0_status(ST0_CU1 | ST0_FR);
+ disable_fpu_hazard();
}
preempt_enable();
}
diff --git a/arch/mips/kvm/tlb.c b/arch/mips/kvm/tlb.c
index e0e1d0a..60e4ad0 100644
--- a/arch/mips/kvm/tlb.c
+++ b/arch/mips/kvm/tlb.c
@@ -268,6 +268,7 @@
int even;
struct kvm *kvm = vcpu->kvm;
const int flush_dcache_mask = 0;
+ int ret;
if (KVM_GUEST_KSEGX(badvaddr) != KVM_GUEST_KSEG0) {
kvm_err("%s: Invalid BadVaddr: %#lx\n", __func__, badvaddr);
@@ -299,14 +300,18 @@
pfn1 = kvm->arch.guest_pmap[gfn];
}
- entryhi = (vaddr | kvm_mips_get_kernel_asid(vcpu));
entrylo0 = mips3_paddr_to_tlbpfn(pfn0 << PAGE_SHIFT) | (0x3 << 3) |
(1 << 2) | (0x1 << 1);
entrylo1 = mips3_paddr_to_tlbpfn(pfn1 << PAGE_SHIFT) | (0x3 << 3) |
(1 << 2) | (0x1 << 1);
- return kvm_mips_host_tlb_write(vcpu, entryhi, entrylo0, entrylo1,
- flush_dcache_mask);
+ preempt_disable();
+ entryhi = (vaddr | kvm_mips_get_kernel_asid(vcpu));
+ ret = kvm_mips_host_tlb_write(vcpu, entryhi, entrylo0, entrylo1,
+ flush_dcache_mask);
+ preempt_enable();
+
+ return ret;
}
EXPORT_SYMBOL_GPL(kvm_mips_handle_kseg0_tlb_fault);
@@ -361,6 +366,7 @@
unsigned long entryhi = 0, entrylo0 = 0, entrylo1 = 0;
struct kvm *kvm = vcpu->kvm;
kvm_pfn_t pfn0, pfn1;
+ int ret;
if ((tlb->tlb_hi & VPN2_MASK) == 0) {
pfn0 = 0;
@@ -387,9 +393,6 @@
*hpa1 = pfn1 << PAGE_SHIFT;
/* Get attributes from the Guest TLB */
- entryhi = (tlb->tlb_hi & VPN2_MASK) | (KVM_GUEST_KERNEL_MODE(vcpu) ?
- kvm_mips_get_kernel_asid(vcpu) :
- kvm_mips_get_user_asid(vcpu));
entrylo0 = mips3_paddr_to_tlbpfn(pfn0 << PAGE_SHIFT) | (0x3 << 3) |
(tlb->tlb_lo0 & MIPS3_PG_D) | (tlb->tlb_lo0 & MIPS3_PG_V);
entrylo1 = mips3_paddr_to_tlbpfn(pfn1 << PAGE_SHIFT) | (0x3 << 3) |
@@ -398,8 +401,15 @@
kvm_debug("@ %#lx tlb_lo0: 0x%08lx tlb_lo1: 0x%08lx\n", vcpu->arch.pc,
tlb->tlb_lo0, tlb->tlb_lo1);
- return kvm_mips_host_tlb_write(vcpu, entryhi, entrylo0, entrylo1,
- tlb->tlb_mask);
+ preempt_disable();
+ entryhi = (tlb->tlb_hi & VPN2_MASK) | (KVM_GUEST_KERNEL_MODE(vcpu) ?
+ kvm_mips_get_kernel_asid(vcpu) :
+ kvm_mips_get_user_asid(vcpu));
+ ret = kvm_mips_host_tlb_write(vcpu, entryhi, entrylo0, entrylo1,
+ tlb->tlb_mask);
+ preempt_enable();
+
+ return ret;
}
EXPORT_SYMBOL_GPL(kvm_mips_handle_mapped_seg_tlb_fault);
diff --git a/arch/mips/kvm/trap_emul.c b/arch/mips/kvm/trap_emul.c
index c4038d2..caa5ea1 100644
--- a/arch/mips/kvm/trap_emul.c
+++ b/arch/mips/kvm/trap_emul.c
@@ -546,7 +546,7 @@
kvm_mips_write_count(vcpu, v);
break;
case KVM_REG_MIPS_CP0_COMPARE:
- kvm_mips_write_compare(vcpu, v);
+ kvm_mips_write_compare(vcpu, v, false);
break;
case KVM_REG_MIPS_CP0_CAUSE:
/*
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index b7e3944..c66e262 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -562,7 +562,6 @@
struct {
u64 msr_val;
u64 last_steal;
- u64 accum_steal;
struct gfn_to_hva_cache stime;
struct kvm_steal_time steal;
} st;
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index cd54147..739c0c5 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -216,9 +216,9 @@
__u32 padding[3];
};
-#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX BIT(0)
-#define KVM_CPUID_FLAG_STATEFUL_FUNC BIT(1)
-#define KVM_CPUID_FLAG_STATE_READ_NEXT BIT(2)
+#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX (1 << 0)
+#define KVM_CPUID_FLAG_STATEFUL_FUNC (1 << 1)
+#define KVM_CPUID_FLAG_STATE_READ_NEXT (1 << 2)
/* for KVM_SET_CPUID2 */
struct kvm_cpuid2 {
diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
index 54ead79..dfb4c64 100644
--- a/arch/x86/kvm/irq_comm.c
+++ b/arch/x86/kvm/irq_comm.c
@@ -382,9 +382,6 @@
u32 i, nr_ioapic_pins;
int idx;
- /* kvm->irq_routing must be read after clearing
- * KVM_SCAN_IOAPIC. */
- smp_mb();
idx = srcu_read_lock(&kvm->irq_srcu);
table = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
nr_ioapic_pins = min_t(u32, table->nr_rt_entries,
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 1ff4dbb..850335a 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1909,18 +1909,17 @@
* since it has been deleted from active_mmu_pages but still can be found
* at hast list.
*
- * for_each_gfn_indirect_valid_sp has skipped that kind of page and
- * kvm_mmu_get_page(), the only user of for_each_gfn_sp(), has skipped
- * all the obsolete pages.
+ * for_each_gfn_valid_sp() has skipped that kind of pages.
*/
-#define for_each_gfn_sp(_kvm, _sp, _gfn) \
+#define for_each_gfn_valid_sp(_kvm, _sp, _gfn) \
hlist_for_each_entry(_sp, \
&(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)], hash_link) \
- if ((_sp)->gfn != (_gfn)) {} else
+ if ((_sp)->gfn != (_gfn) || is_obsolete_sp((_kvm), (_sp)) \
+ || (_sp)->role.invalid) {} else
#define for_each_gfn_indirect_valid_sp(_kvm, _sp, _gfn) \
- for_each_gfn_sp(_kvm, _sp, _gfn) \
- if ((_sp)->role.direct || (_sp)->role.invalid) {} else
+ for_each_gfn_valid_sp(_kvm, _sp, _gfn) \
+ if ((_sp)->role.direct) {} else
/* @sp->gfn should be write-protected at the call site */
static bool __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
@@ -1961,6 +1960,11 @@
static void mmu_audit_disable(void) { }
#endif
+static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+ return unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen);
+}
+
static bool kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
struct list_head *invalid_list)
{
@@ -2105,11 +2109,6 @@
__clear_sp_write_flooding_count(sp);
}
-static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
-{
- return unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen);
-}
-
static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
gfn_t gfn,
gva_t gaddr,
@@ -2136,10 +2135,7 @@
quadrant &= (1 << ((PT32_PT_BITS - PT64_PT_BITS) * level)) - 1;
role.quadrant = quadrant;
}
- for_each_gfn_sp(vcpu->kvm, sp, gfn) {
- if (is_obsolete_sp(vcpu->kvm, sp))
- continue;
-
+ for_each_gfn_valid_sp(vcpu->kvm, sp, gfn) {
if (!need_sync && sp->unsync)
need_sync = true;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index ee1c8a9..ab4a387 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -5046,8 +5046,8 @@
vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET;
- vmx_set_cr0(vcpu, cr0); /* enter rmode */
vmx->vcpu.arch.cr0 = cr0;
+ vmx_set_cr0(vcpu, cr0); /* enter rmode */
vmx_set_cr4(vcpu, 0);
vmx_set_efer(vcpu, 0);
vmx_fpu_activate(vcpu);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 9b7798c..57a62d1 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2002,22 +2002,8 @@
vcpu->arch.pv_time_enabled = false;
}
-static void accumulate_steal_time(struct kvm_vcpu *vcpu)
-{
- u64 delta;
-
- if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
- return;
-
- delta = current->sched_info.run_delay - vcpu->arch.st.last_steal;
- vcpu->arch.st.last_steal = current->sched_info.run_delay;
- vcpu->arch.st.accum_steal = delta;
-}
-
static void record_steal_time(struct kvm_vcpu *vcpu)
{
- accumulate_steal_time(vcpu);
-
if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
return;
@@ -2025,9 +2011,26 @@
&vcpu->arch.st.steal, sizeof(struct kvm_steal_time))))
return;
- vcpu->arch.st.steal.steal += vcpu->arch.st.accum_steal;
- vcpu->arch.st.steal.version += 2;
- vcpu->arch.st.accum_steal = 0;
+ if (vcpu->arch.st.steal.version & 1)
+ vcpu->arch.st.steal.version += 1; /* first time write, random junk */
+
+ vcpu->arch.st.steal.version += 1;
+
+ kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
+ &vcpu->arch.st.steal, sizeof(struct kvm_steal_time));
+
+ smp_wmb();
+
+ vcpu->arch.st.steal.steal += current->sched_info.run_delay -
+ vcpu->arch.st.last_steal;
+ vcpu->arch.st.last_steal = current->sched_info.run_delay;
+
+ kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
+ &vcpu->arch.st.steal, sizeof(struct kvm_steal_time));
+
+ smp_wmb();
+
+ vcpu->arch.st.steal.version += 1;
kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
&vcpu->arch.st.steal, sizeof(struct kvm_steal_time));
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 5276fe0..ad40d44 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1091,6 +1091,11 @@
static inline void kvm_make_request(int req, struct kvm_vcpu *vcpu)
{
+ /*
+ * Ensure the rest of the request is published to kvm_check_request's
+ * caller. Paired with the smp_mb__after_atomic in kvm_check_request.
+ */
+ smp_wmb();
set_bit(req, &vcpu->requests);
}
@@ -1098,6 +1103,12 @@
{
if (test_bit(req, &vcpu->requests)) {
clear_bit(req, &vcpu->requests);
+
+ /*
+ * Ensure the rest of the request is visible to kvm_check_request's
+ * caller. Paired with the smp_wmb in kvm_make_request.
+ */
+ smp_mb__after_atomic();
return true;
} else {
return false;